# Hyperbrowser

## Docs

- [Browser-Use](https://hyperbrowser.ai/docs/agents/browser-use.md): Fast and efficient browser automation with the open-source browser-use framework
- [Claude Computer Use](https://hyperbrowser.ai/docs/agents/claude-computer-use.md): Automate browser tasks using Anthropic's Claude with sophisticated computer use capabilities
- [Gemini Computer Use](https://hyperbrowser.ai/docs/agents/gemini-computer-use.md): Automate browser tasks with Google's Gemini computer use capabilities
- [HyperAgent](https://hyperbrowser.ai/docs/agents/hyperagent.md): Execute AI agent tasks using HyperAgent, our open-source Playwright-powered framework
- [OpenAI CUA](https://hyperbrowser.ai/docs/agents/openai-cua.md): Execute AI agent tasks using OpenAI's Computer-Using Agent
- [Overview](https://hyperbrowser.ai/docs/agents/overview.md): Use AI agents to easily automate browser tasks and create agentic workflows
- [Add a new extension](https://hyperbrowser.ai/docs/api-reference/add-a-new-extension.md)
- [Create new scrape job](https://hyperbrowser.ai/docs/api-reference/create-new-scrape-job.md)
- [Create new session](https://hyperbrowser.ai/docs/api-reference/create-new-session.md)
- [Creates a new profile](https://hyperbrowser.ai/docs/api-reference/creates-a-new-profile.md)
- [Delete profile by ID](https://hyperbrowser.ai/docs/api-reference/delete-profile-by-id.md)
- [Fetch a web page](https://hyperbrowser.ai/docs/api-reference/fetch-a-web-page.md): Fetches a web page and returns the content in various formats (HTML, Markdown, JSON, screenshot, etc.)
- [Fetch a web page with X402 payment](https://hyperbrowser.ai/docs/api-reference/fetch-a-web-page-with-x402-payment.md): X402 payment endpoint. First request returns 402 with payment requirements. Retry with PAYMENT-SIGNATURE header containing cryptographic proof to get the actual data. See https://x402.gitbook.io/x402 for protocol details.
- [Get batch scrape job status](https://hyperbrowser.ai/docs/api-reference/get-batch-scrape-job-status.md)
- [Get batch scrape job status and results](https://hyperbrowser.ai/docs/api-reference/get-batch-scrape-job-status-and-results.md)
- [Get browser use task status](https://hyperbrowser.ai/docs/api-reference/get-browser-use-task-status.md)
- [Get browser use task status and results](https://hyperbrowser.ai/docs/api-reference/get-browser-use-task-status-and-results.md)
- [Get claude computer use task status](https://hyperbrowser.ai/docs/api-reference/get-claude-computer-use-task-status.md)
- [Get claude computer use task status and results](https://hyperbrowser.ai/docs/api-reference/get-claude-computer-use-task-status-and-results.md)
- [Get crawl job status](https://hyperbrowser.ai/docs/api-reference/get-crawl-job-status.md)
- [Get crawl job status and results](https://hyperbrowser.ai/docs/api-reference/get-crawl-job-status-and-results.md)
- [Get CUA task status](https://hyperbrowser.ai/docs/api-reference/get-cua-task-status.md)
- [Get CUA task status and results](https://hyperbrowser.ai/docs/api-reference/get-cua-task-status-and-results.md)
- [Get extract job status](https://hyperbrowser.ai/docs/api-reference/get-extract-job-status.md)
- [Get extract job status and results](https://hyperbrowser.ai/docs/api-reference/get-extract-job-status-and-results.md)
- [Get gemini computer use task status](https://hyperbrowser.ai/docs/api-reference/get-gemini-computer-use-task-status.md)
- [Get gemini computer use task status and results](https://hyperbrowser.ai/docs/api-reference/get-gemini-computer-use-task-status-and-results.md)
- [Get HyperAgent task status](https://hyperbrowser.ai/docs/api-reference/get-hyperagent-task-status.md)
- [Get HyperAgent task status and results](https://hyperbrowser.ai/docs/api-reference/get-hyperagent-task-status-and-results.md)
- [Get list of profiles](https://hyperbrowser.ai/docs/api-reference/get-list-of-profiles.md)
- [Get list of sessions](https://hyperbrowser.ai/docs/api-reference/get-list-of-sessions.md)
- [Get profile by ID](https://hyperbrowser.ai/docs/api-reference/get-profile-by-id.md)
- [Get scrape job status](https://hyperbrowser.ai/docs/api-reference/get-scrape-job-status.md)
- [Get scrape job status and result](https://hyperbrowser.ai/docs/api-reference/get-scrape-job-status-and-result.md)
- [Get session by ID](https://hyperbrowser.ai/docs/api-reference/get-session-by-id.md)
- [Get session downloads URL](https://hyperbrowser.ai/docs/api-reference/get-session-downloads-url.md)
- [Get session recording URL](https://hyperbrowser.ai/docs/api-reference/get-session-recording-url.md)
- [Get session video recording URL](https://hyperbrowser.ai/docs/api-reference/get-session-video-recording-url.md)
- [Get web crawl job results](https://hyperbrowser.ai/docs/api-reference/get-web-crawl-job-results.md): Retrieves the status and results of a web crawl job. Results are paginated.
- [Get web crawl job status](https://hyperbrowser.ai/docs/api-reference/get-web-crawl-job-status.md): Retrieves just the status of a web crawl job without the full results.
- [List all extensions](https://hyperbrowser.ai/docs/api-reference/list-all-extensions.md)
- [Search the web](https://hyperbrowser.ai/docs/api-reference/search-the-web.md): Performs a web search and returns search results with titles, URLs, and descriptions
- [Search the web with X402 payment](https://hyperbrowser.ai/docs/api-reference/search-the-web-with-x402-payment.md): X402 payment endpoint. First request returns 402 with payment requirements. Retry with PAYMENT-SIGNATURE header containing cryptographic proof to get search results. See https://x402.gitbook.io/x402 for protocol details.
- [Start a batch scrape job](https://hyperbrowser.ai/docs/api-reference/start-a-batch-scrape-job.md)
- [Start a browser use task](https://hyperbrowser.ai/docs/api-reference/start-a-browser-use-task.md)
- [Start a claude computer use task](https://hyperbrowser.ai/docs/api-reference/start-a-claude-computer-use-task.md)
- [Start a crawl job](https://hyperbrowser.ai/docs/api-reference/start-a-crawl-job.md)
- [Start a CUA task](https://hyperbrowser.ai/docs/api-reference/start-a-cua-task.md)
- [Start a gemini computer use task](https://hyperbrowser.ai/docs/api-reference/start-a-gemini-computer-use-task.md)
- [Start a HyperAgent task](https://hyperbrowser.ai/docs/api-reference/start-a-hyperagent-task.md)
- [Start a web crawl job](https://hyperbrowser.ai/docs/api-reference/start-a-web-crawl-job.md): Starts an asynchronous crawl job that follows links from a starting URL and returns content from each page in the specified formats.
- [Start an extract job](https://hyperbrowser.ai/docs/api-reference/start-an-extract-job.md)
- [Stop a browser use task](https://hyperbrowser.ai/docs/api-reference/stop-a-browser-use-task.md)
- [Stop a claude computer use task](https://hyperbrowser.ai/docs/api-reference/stop-a-claude-computer-use-task.md)
- [Stop a CUA task](https://hyperbrowser.ai/docs/api-reference/stop-a-cua-task.md)
- [Stop a gemini computer use task](https://hyperbrowser.ai/docs/api-reference/stop-a-gemini-computer-use-task.md)
- [Stop a HyperAgent task](https://hyperbrowser.ai/docs/api-reference/stop-a-hyperagent-task.md)
- [Stop a session](https://hyperbrowser.ai/docs/api-reference/stop-a-session.md)
- [Home](https://hyperbrowser.ai/docs/home.md): Fast Cloud Browsers for AI Agents and Automation
- [Action Caching](https://hyperbrowser.ai/docs/hyperagent/action-cache.md): Record and replay browser automation tasks without LLM calls for fast, deterministic execution
- [HyperBrowser Provider](https://hyperbrowser.ai/docs/hyperagent/browser-providers.md): Run HyperAgent locally or scale to the cloud with Hyperbrowser
- [Custom Actions](https://hyperbrowser.ai/docs/hyperagent/custom-actions.md): Extend HyperAgent with custom actions for specialized workflows
- [page.extract()](https://hyperbrowser.ai/docs/hyperagent/extract.md): Extract structured data from web pages using natural language and Zod schemas
- [LLM Providers](https://hyperbrowser.ai/docs/hyperagent/llm-providers.md): Configure OpenAI, Anthropic, Google Gemini as your LLM provider
- [MCP Integration](https://hyperbrowser.ai/docs/hyperagent/mcp.md): Connect HyperAgent to MCP servers for extended capabilities
- [Multi-Page Management](https://hyperbrowser.ai/docs/hyperagent/multi-page.md): Manage multiple browser pages and tabs simultaneously
- [Overview](https://hyperbrowser.ai/docs/hyperagent/overview.md): Use HyperAgent to automate browser tasks with AI
- [page.ai()](https://hyperbrowser.ai/docs/hyperagent/page-ai.md): Execute complex multi-step browser tasks with AI-powered automation
- [page.perform()](https://hyperbrowser.ai/docs/hyperagent/page-perform.md): Execute fast, single-action browser interactions using natural language
- [Quickstart](https://hyperbrowser.ai/docs/hyperagent/quickstart.md): Build your first HyperAgent automation in under a minute
- [AI Function Calling](https://hyperbrowser.ai/docs/integrations/ai-function-calling.md): Integrate Hyperbrowser scrape, crawl, and extract tools with OpenAI and Anthropic function calling
- [LangChain](https://hyperbrowser.ai/docs/integrations/langchain.md): Integrate Hyperbrowser with LangChain for web scraping and document loading
- [LlamaIndex](https://hyperbrowser.ai/docs/integrations/llamaindex.md): Integrate Hyperbrowser with LlamaIndex for web scraping and document loading
- [Model Context Protocol](https://hyperbrowser.ai/docs/integrations/model-context-protocol.md): Use Hyperbrowser with the Model Context Protocol (MCP) to enable web automation tools for AI models
- [Stagehand](https://hyperbrowser.ai/docs/integrations/stagehand.md): Run Stagehand automations on Hyperbrowser's managed browser sessions.
- [X402](https://hyperbrowser.ai/docs/integrations/x402.md): Enable autonomous agent payments with X402 protocol
- [Introduction](https://hyperbrowser.ai/docs/introduction.md): Fast Cloud Browsers for your AI Agents
- [Pricing](https://hyperbrowser.ai/docs/pricing.md): Understand how Hyperbrowser credits work and pricing for all services
- [Quickstart](https://hyperbrowser.ai/docs/quickstart.md): Start automating with Hyperbrowser Sessions
- [Base Images](https://hyperbrowser.ai/docs/sandboxes/base-images.md)
- [Sandbox CLI](https://hyperbrowser.ai/docs/sandboxes/cli.md): Use the Hyperbrowser CLI to create and manage sandboxes
- [Creating Sandboxes](https://hyperbrowser.ai/docs/sandboxes/create.md): Create and configure Hyperbrowser sandboxes
- [Build And Upload A Custom Image](https://hyperbrowser.ai/docs/sandboxes/custom-images.md): Package a local Docker image into a Hyperbrowser sandbox image with the CLI
- [Overview](https://hyperbrowser.ai/docs/sandboxes/filesystem/overview.md): Understand the sandbox local filesystem surface and the operations available on it
- [Read And Write Operations](https://hyperbrowser.ai/docs/sandboxes/filesystem/read-write.md): Read, write, inspect, and manage files and directories inside a sandbox
- [Upload, Download, And Presigned URLs](https://hyperbrowser.ai/docs/sandboxes/filesystem/transfers.md): Transfer file contents into and out of a sandbox with direct and presigned operations
- [Watch](https://hyperbrowser.ai/docs/sandboxes/filesystem/watch.md): Stream file system events from a sandbox directory or path
- [Install](https://hyperbrowser.ai/docs/sandboxes/install.md): Install the Hyperbrowser SDKs and the hx CLI
- [Introduction](https://hyperbrowser.ai/docs/sandboxes/introduction.md): Run your agents in the cloud fully harnessed
- [Sandbox Lifecycle](https://hyperbrowser.ai/docs/sandboxes/lifecycle.md)
- [OpenClaw + WhatsApp](https://hyperbrowser.ai/docs/sandboxes/openclaw-whatsapp.md): Connect OpenClaw to WhatsApp in a Hyperbrowser sandbox
- [Sandbox Processes](https://hyperbrowser.ai/docs/sandboxes/processes.md)
- [Sandbox Runtime URLs](https://hyperbrowser.ai/docs/sandboxes/runtime.md): Understand runtime URLs, exposed ports, and authenticated browser access
- [Sandbox Snapshots](https://hyperbrowser.ai/docs/sandboxes/snapshots.md): Create memory snapshots and start sandboxes from snapshots
- [Sandbox Terminal](https://hyperbrowser.ai/docs/sandboxes/terminal.md): Open interactive terminal sessions inside a sandbox
- [Overview](https://hyperbrowser.ai/docs/sandboxes/volumes.md): Persistent storage that can be mounted into sandboxes
- [Read and Write Mounted Volume Data](https://hyperbrowser.ai/docs/sandboxes/volumes/data-access.md): Work with volume files through mounted paths
- [Managing Volumes](https://hyperbrowser.ai/docs/sandboxes/volumes/managing.md)
- [Mounting Volumes](https://hyperbrowser.ai/docs/sandboxes/volumes/mounting.md): Attach volumes to sandboxes at launch
- [Introduction](https://hyperbrowser.ai/docs/sdks/introduction.md): Official SDKs for integrating Hyperbrowser into your applications
- [Node SDK](https://hyperbrowser.ai/docs/sdks/node.md): Complete guide to the Hyperbrowser Node.js SDK
- [Python SDK](https://hyperbrowser.ai/docs/sdks/python.md): Complete guide to the Hyperbrowser Python SDK
- [Ad Blocking](https://hyperbrowser.ai/docs/sessions/ad-blocking.md): Learn how to block ads and trackers in your browser sessions
- [CAPTCHA Solving](https://hyperbrowser.ai/docs/sessions/captcha-solving.md): Learn how to solve CAPTCHAs in your browser sessions
- [Computer Actions](https://hyperbrowser.ai/docs/sessions/computer-actions.md): Control sessions with low-level mouse and keyboard input
- [Configuring Sessions](https://hyperbrowser.ai/docs/sessions/create.md): Learn how to create and configure Hyperbrowser sessions
- [File Downloads](https://hyperbrowser.ai/docs/sessions/downloads.md): Save and retrieve files downloaded during browser sessions
- [Browser Extensions](https://hyperbrowser.ai/docs/sessions/extensions.md): Load custom Chrome extensions into your browser sessions
- [Session Lifecycle](https://hyperbrowser.ai/docs/sessions/lifecycle.md): Manage the lifecycle of your Hyperbrowser sessions
- [Live View](https://hyperbrowser.ai/docs/sessions/live-view.md): Watch and interact with your browser sessions in real-time
- [Session Parameters](https://hyperbrowser.ai/docs/sessions/parameters.md): Learn about the parameters that can be used to configure Hyperbrowser sessions
- [Connect with Playwright](https://hyperbrowser.ai/docs/sessions/playwright.md): Control Hyperbrowser sessions using Playwright
- [Profiles](https://hyperbrowser.ai/docs/sessions/profiles.md): Persist browser state across sessions
- [Proxy Configuration](https://hyperbrowser.ai/docs/sessions/proxy.md): Route your sessions through proxy servers for geo-targeting and IP rotation
- [Connect with Puppeteer](https://hyperbrowser.ai/docs/sessions/puppeteer.md): Control Hyperbrowser sessions using Puppeteer
- [Recordings](https://hyperbrowser.ai/docs/sessions/recordings.md): Record and replay your browser sessions with web recordings and video replays
- [Multi-Region Support](https://hyperbrowser.ai/docs/sessions/regions.md): Deploy browser sessions across multiple geographic regions for optimal performance and compliance
- [Connect with Selenium](https://hyperbrowser.ai/docs/sessions/selenium.md): Control Hyperbrowser sessions using Selenium
- [Static IPs](https://hyperbrowser.ai/docs/sessions/static-ips.md): Use dedicated IP addresses for your sessions
- [Stealth Mode](https://hyperbrowser.ai/docs/sessions/stealth.md): Configure anti-detection features for your browser sessions
- [File Uploads](https://hyperbrowser.ai/docs/sessions/uploads.md): Learn how to upload files to your browser sessions
- [Advanced Guide](https://hyperbrowser.ai/docs/web-scraping/advanced-guide.md): End-to-end guide to scrape, crawl, and extract structured data
- [Crawl](https://hyperbrowser.ai/docs/web-scraping/crawl.md): Crawl websites and get formatted data from multiple pages
- [Extract](https://hyperbrowser.ai/docs/web-scraping/extract.md): Extract structured data from web pages using AI
- [Scrape](https://hyperbrowser.ai/docs/web-scraping/scrape.md): Scrape any page and get formatted data
- [Crawl](https://hyperbrowser.ai/docs/web/crawl.md): Crawl a website and get structured data from multiple pages
- [Fetch](https://hyperbrowser.ai/docs/web/fetch.md): Fetch any page and get data in the formats you choose
- [Overview](https://hyperbrowser.ai/docs/web/overview.md): Fetch pages, crawl sites, and search the web
- [Search](https://hyperbrowser.ai/docs/web/search.md): Query the web and get clean, structured results

## OpenAPI Specs

- [openapi](https://hyperbrowser.ai/docs/openapi.json)